General model by nvidia · 123.61B parameters
NVIDIA Nemotron 3 Super 120B A12B FP8 requires 54.3 GB which exceeds your available memory. You need a Mac with more RAM.
| Quantization | Memory | Speed | Fits? |
|---|---|---|---|
| Q8_0 | 138.4 GB | ~1 tok/s | ✗ |
| Q6_K | 107.5 GB | ~2 tok/s | ✗ |
| Q5_K_M | 92.7 GB | ~2 tok/s | ✗ |
| Q4_K_M | 80.3 GB | ~2 tok/s | ✗ |
| Q3_K_M | 67.9 GB | ~3 tok/s | ✗ |
| Q2_K | 54.3 GB | ~4 tok/s | ✗ |
ToolPiper downloads, manages, and runs models with one click. Apple Silicon optimized.
Get ToolPiper — Free